Merge branch 'mc/clean-smudge-with-llp64'

The clean/smudge conversion code path has been prepared to better
work on platforms where ulong is narrower than size_t.

* mc/clean-smudge-with-llp64:
  clean/smudge: allow clean filters to process extremely large files
  odb: guard against data loss checking out a huge file
  git-compat-util: introduce more size_t helpers
  odb: teach read_blob_entry to use size_t
  t1051: introduce a smudge filter test for extremely large files
  test-lib: add prerequisite for 64-bit platforms
  test-tool genzeros: generate large amounts of data more efficiently
  test-genzeros: allow more than 2G zeros in Windows

3 files changed, 47 insertions, 4 deletions

diff --git a/t/helper/test-genzeros.c b/t/helper/test-genzeros.c
index 9532f5bac9..8ca988d621 100644
--- a/t/helper/test-genzeros.c
+++ b/t/helper/test-genzeros.c
@@ -3,18 +3,31 @@
 
 int cmd__genzeros(int argc, const char **argv)
 {
-	long count;
+	/* static, so that it is NUL-initialized */
+	static const char zeros[256 * 1024];
+	intmax_t count;
+	ssize_t n;
 
 	if (argc > 2) {
 		fprintf(stderr, "usage: %s [<count>]\n", argv[0]);
 		return 1;
 	}
 
-	count = argc > 1 ? strtol(argv[1], NULL, 0) : -1L;
+	count = argc > 1 ? strtoimax(argv[1], NULL, 0) : -1;
 
-	while (count < 0 || count--) {
-		if (putchar(0) == EOF)
+	/* Writing out individual NUL bytes is slow... */
+	while (count < 0)
+		if (write(1, zeros, ARRAY_SIZE(zeros)) < 0)
 			return -1;
+
+	while (count > 0) {
+		n = write(1, zeros, count < ARRAY_SIZE(zeros) ?
+			  count : ARRAY_SIZE(zeros));
+
+		if (n < 0)
+			return -1;
+
+		count -= n;
 	}
 
 	return 0;
diff --git a/t/t1051-large-conversion.sh b/t/t1051-large-conversion.sh
index 8b7640b3ba..042b0e4429 100755
--- a/t/t1051-large-conversion.sh
+++ b/t/t1051-large-conversion.sh
@@ -83,4 +83,30 @@ test_expect_success 'ident converts on output' '
 	test_cmp small.clean large.clean
 '
 
+# This smudge filter prepends 5GB of zeros to the file it checks out. This
+# ensures that smudging doesn't mangle large files on 64-bit Windows.
+test_expect_success EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
+		'files over 4GB convert on output' '
+	test_commit test small "a small file" &&
+	small_size=$(test_file_size small) &&
+	test_config filter.makelarge.smudge \
+		"test-tool genzeros $((5*1024*1024*1024)) && cat" &&
+	echo "small filter=makelarge" >.gitattributes &&
+	rm small &&
+	git checkout -- small &&
+	size=$(test_file_size small) &&
+	test "$size" -eq $((5 * 1024 * 1024 * 1024 + $small_size))
+'
+
+# This clean filter writes down the size of input it receives. By checking against
+# the actual size, we ensure that cleaning doesn't mangle large files on 64-bit Windows.
+test_expect_success EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
+		'files over 4GB convert on input' '
+	test-tool genzeros $((5*1024*1024*1024)) >big &&
+	test_config filter.checklarge.clean "wc -c >big.size" &&
+	echo "big filter=checklarge" >.gitattributes &&
+	git add big &&
+	test $(test_file_size big) -eq $(cat big.size)
+'
+
 test_done
diff --git a/t/test-lib.sh b/t/test-lib.sh
index 2679a7596a..57efcc5e97 100644
--- a/t/test-lib.sh
+++ b/t/test-lib.sh
@@ -1734,6 +1734,10 @@ build_option () {
 	sed -ne "s/^$1: //p"
 }
 
+test_lazy_prereq SIZE_T_IS_64BIT '
+	test 8 -eq "$(build_option sizeof-size_t)"
+'
+
 test_lazy_prereq LONG_IS_64BIT '
 	test 8 -le "$(build_option sizeof-long)"
 '